Well from the article a dataset is required, but not always the heavier one.
Tho it doesn’t solve the speed issue, where the llm will take a lot more time to do the compression.
gzip can compress 1GB of text in less than a minute on a CPU, an LLM with 3.2 million parameters requires an hour to compress
I guess the offline it’s mostly to advertise privacy. Or maybe can it translate pdf documents?